|
89620b9169
|
[NPU] Support DeepSeek V4 Flash MTP on Ascend (#28980)
Co-authored-by: Kurkur <mccllm@qq.com>
Co-authored-by: gjsheu <gjsheu@163.com>
Co-authored-by: root <root@localhost.localdomain>
Co-authored-by: khalil2ji3mp6 <khalilzhk@gmail.com>
|
2026-06-30 16:22:13 +08:00 |
|
|
cctryandcctry
|
4b4b4af583
|
Budget EAGLE/STANDALONE draft KV pool in SWA pool configurators (#29622)
Co-authored-by: cctry <cctry@fb.com>
|
2026-06-30 00:58:33 -07:00 |
|
|
silencejade
|
ff51acd67b
|
[NPU] Qwen3-VL-8B use split_qkv_rmsnorm_rope for extend (#29627)
|
2026-06-30 15:55:50 +08:00 |
|
|
Mohammad Miadh Angkad
|
bae78a44da
|
[Deps] Bump transformers to 5.12.1 (#29393)
|
2026-06-30 00:54:01 -07:00 |
|
|
Thomas Wang
|
f920a37da4
|
[AMD] Copy decode result on forward_stream instead of copy_stream (#29642)
|
2026-06-29 23:53:48 -07:00 |
|
|
Mohammad Miadh Angkad
|
b6fceaa789
|
[DSA] Use cos_sin_cache for DSA indexer fusion (#29613)
|
2026-06-29 23:49:00 -07:00 |
|
|
|
54e71506b3
|
[AMD][DSV4] Remove per-batch D2H syncs in MTP to avoid bubbles between 2 batches (#29420)
Co-authored-by: amd-danli103 <amd-danli103@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
|
2026-06-29 22:39:59 -07:00 |
|
|
yifei wuandXinyuan Tong
|
f41d455f37
|
[Model] Add HrmTextForCausalLM (Hierarchical Reasoning Model - Text) (#27887)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-06-30 13:32:32 +08:00 |
|
|
Mick
|
2068ae7eec
|
[diffusion] chore: document VAE decode parallel group axes (#29364)
|
2026-06-30 12:14:55 +08:00 |
|
|
Xiaoyu ZhangandClaude Opus 4.8
|
3add35e26d
|
[Diffusion] Reuse shared AlignedVector and tidy jit_kernel/diffusion (#29664)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-30 11:38:22 +08:00 |
|
|
Mohammad Miadh Angkad
|
3a72d02415
|
[DSA] Optimize DSA CUDA graph replay metadata generation (#29499)
|
2026-06-29 19:53:23 -07:00 |
|
|
Mick
|
25b6051c70
|
[diffusion] warmup: default to model sampling resolution (declare Z-Image default) (#29519)
|
2026-06-30 10:32:11 +08:00 |
|
|
Ho-Ren (Jack) Chuang
|
bc8b3ab1f5
|
[Kernel] Add SM90 Q8KV8 FP8 Sparse MLA Prefill JIT Kernel with Tests and Benchmark (#25751)
|
2026-06-30 09:00:11 +08:00 |
|
|
Ho-Ren (Jack) Chuang
|
a6bc432fd8
|
[Perf][Kernel] Fuse SiLU+Mul into NVFP4 Expert Quantization for CUTLASS MoE (#18612)
|
2026-06-29 16:51:01 -07:00 |
|
|
eeechoandAliceChenyy
|
f0bf96390b
|
[SM120] Add FlashInfer sparse MLA decode for DSv4-Flash (#27455)
Co-authored-by: AliceChenyy <alicechenyy@users.noreply.github.com>
|
2026-06-29 16:27:16 -07:00 |
|
|
Trevor Morris
|
b8c25bfaa7
|
[NVIDIA] Support flashinfer a2a with flashinfer_trtllm_routed moe (#22394)
|
2026-06-29 16:23:58 -07:00 |
|
|
Khoa PhamandClaude Opus 4.7
|
6bdecb8206
|
[DeepSeek V3] Reland: run routed experts on main stream in dual-stream MoE (#29463)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-06-29 15:05:01 -07:00 |
|
|
Xinyuan Tong
|
45314a9fcb
|
[spec] Fix index_share_for_mtp_iteration being a no-op in EAGLE MTP draft (#29654)
|
2026-06-29 14:52:23 -07:00 |
|
|
Cheng Wanandlch1475369
|
fc96edd297
|
feat(mem_cache): page-major (layer-major within a page) KV/state layout (#29533)
Co-authored-by: lch1475369 <lch1475369@gmail.com>
|
2026-06-29 14:49:54 -07:00 |
|
|
Mohammad Miadh Angkad
|
6c018eb4d1
|
Fix bounded checkpoint prefetching and buffered drop-cache handling (#29156)
|
2026-06-29 21:49:16 +00:00 |
|
|
|
5556631789
|
[Speculative Decoding] Validate vocabulary compatibility in STANDALONE mode (#23838)
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-29 14:45:12 -07:00 |
|
|
Brayden Zhong
|
98d0e702c3
|
[GLM-5] Tune the threshold of router GEMM (#29470)
|
2026-06-29 14:19:24 -07:00 |
|
|
cctryandcctry
|
a5c45a12bb
|
CUDA graph executable dedup via cudaGraphExecUpdate (#29625)
Co-authored-by: cctry <cctry@fb.com>
|
2026-06-29 13:56:33 -07:00 |
|
|
|
f480c5f1f9
|
[Spec] Frozen-KV MTP: delay target KV binding to pool init + reset stale draft out_cache_loc (#29616)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: bef0rewind <490285+ronhuafeng@users.noreply.github.com>
Co-authored-by: AlejandroParedesLT <99832715+AlejandroParedesLT@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-29 11:57:10 -07:00 |
|
|
Mick
|
b0be644133
|
[diffusion] feat: keep image-model auxiliary components resident under auto memory policy (#29649)
|
2026-06-30 01:25:37 +08:00 |
|
|
Feng Yao
|
e6c15f76f3
|
[optimize] fix swa eviction boundary for unfinished inserts (#29350)
|
2026-06-30 00:19:15 +08:00 |
|
|
Jyothirmai KottuandXinyuan Tong
|
473a278dd1
|
model: support nvidia/LocateAnything-3B (#28958)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-06-30 00:16:42 +08:00 |
|
|
McZyWu
|
bb7d3440b5
|
bugfix revise interface get cpu copy for npu mem pool to align with gpu (#29146)
|
2026-06-29 19:30:14 +08:00 |
|
|
danielafrimiandDaniel Afrimi
|
a2b5ce2ed1
|
Add stochastic rounding for FP16 Mamba SSM cache (#26929)
Signed-off-by: Daniel Afrimi <dafrimi@login-lyris01.lyris.clusters.nvidia.com>
Co-authored-by: Daniel Afrimi <dafrimi@login-lyris01.lyris.clusters.nvidia.com>
|
2026-06-29 01:47:09 -07:00 |
|
|
iridiumineandiridiumine
|
d5133e925b
|
[NPU][Bugfix] Add scoring_func for mimo_v2 (#29493)
Co-authored-by: iridiumine <iridiumine@users.noreply.github.com>
|
2026-06-29 16:34:54 +08:00 |
|
|
bef0rewind
|
3b1b512a9a
|
Fix disaggregation receiver ZMQ cleanup (#29570)
|
2026-06-29 16:22:29 +08:00 |
|
|
SSSunzt
|
91cf159696
|
[PP] bugfix: include CP size in PP rank offset (#29571)
|
2026-06-29 16:01:41 +08:00 |
|
|
Liangsheng Yin
|
c0d45cda29
|
[Spec] Add DFLASH basic sanity CI test (#29338)
|
2026-06-28 23:45:05 -07:00 |
|
|
AndyLi429
|
62d7929b3a
|
[NPU][Bugfix] Accept in_capture in Ascend replay metadata (#29598)
|
2026-06-29 14:37:45 +08:00 |
|
|
Yueming Yuan
|
cd91dd0757
|
fix test_weight_checker_comparator assertion and ue8m0 scale unpack (#29623)
|
2026-06-28 23:36:37 -07:00 |
|
|
silencejade
|
f85cc94d82
|
[NPU] Qwen3-VL-30B use split_qkv_rmsnorm_rope for extend (#29505)
|
2026-06-29 14:35:19 +08:00 |
|
|
Lianmin Zheng
|
bb74ed4a8d
|
Replace hasattr with isinstance in SHM feature helpers (#29549)
|
2026-06-28 21:31:28 -07:00 |
|
|
Lianmin Zheng
|
f76e707f59
|
Clean up follow-ups for eagle hidden dim clean up (#29546)
|
2026-06-28 21:30:53 -07:00 |
|
|
Peng Xingchen
|
06fd2efedd
|
[NPU][Bugfix] Fix a ModelSlim loading failure (#29029)
|
2026-06-29 09:53:01 +08:00 |
|
|
Liangsheng Yin
|
be17475a1b
|
[Spec] Publish DFLASH verify read-done event for fine-grained WAR barrier (#29541)
|
2026-06-28 18:51:38 -07:00 |
|
|
Yueming Yuan
|
e1ca92a7fd
|
[weight checker] refactor: add precision branch; allow ULP quant err; used chunked compare (#28974)
|
2026-06-28 18:44:05 -07:00 |
|
|
Liangsheng Yin
|
909123ddb8
|
[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591)
|
2026-06-28 18:38:28 -07:00 |
|
|
Ma Mingfei
|
3217410cf6
|
[CPU] enable fused_sigmoid_mul on CPU device (#29378)
|
2026-06-29 09:38:04 +08:00 |
|
|
Polisetty V R K Jyothendra Varma
|
d5abafcc1c
|
[Intel GPU] add pytorch profiling support for XPU in bench offline throughput and enhance num steps (#28308)
Signed-off-by: P V R K Jyothendra Varma <polisettyvarma@gmail.com>
|
2026-06-29 09:10:15 +08:00 |
|
|
Liangsheng Yin
|
abaee4664e
|
[dflash] fa3/fa4: device-side page table; drop seq_lens_cpu D2H sync (#29343)
|
2026-06-28 18:06:33 -07:00 |
|
|
Chao Shi
|
bd2a5db987
|
[HiCache] Detect for double-free in HostKVCache (#29310)
|
2026-06-29 09:02:21 +08:00 |
|
|
Brayden ZhongandBrayden Zhong
|
b9b860652e
|
Fix DSA indexer fusion bug causing excessive memory consumption. (#29576)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-06-28 14:11:07 -07:00 |
|
|
Aurick Qiao
|
ad30a9958e
|
Fix dummy weight init for tensor subclasses (#29229)
|
2026-06-29 01:17:00 +08:00 |
|
|
Yinghai Lu
|
c5b9388721
|
[scheduler] Add scheduler metrics reporter init hook (#29535)
|
2026-06-28 09:59:34 -07:00 |
|
|
ishandhanani
|
aaa31eb0a1
|
feat: first-class session identity in SGLang (#29436)
|
2026-06-28 07:16:38 -07:00 |
|